LoRA from train_dreambooth_lora_sdxl.py is not working in A1111 anymore #6896
Unanswered
patryk-bartkowiak-nitid
asked this question in
Q&A
Replies: 1 comment
-
No need to duplicate the issues and discussions 😅 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I have been using train_dreambooth_lora_sdxl.py and convert_diffusers_sdxl_lora_to_webui.py to train LoRA for specific character, It was working till like a week ago. I am using the same baseline model and the same data.
I realized that previous size of all the LoRA files had 29967176 bytes, now it has 29889672 and less keys in dict after I load it as pure .safetensors file.
I realized that it works fine with inference guide in README:
But after I convert and load to A1111 (it loads correctly) it doesnt work anymore, looks like its adding some noise to the output only.
I already tried checkpointing to previous commits on diffusers, torch and torchvision, but nothing really helps. I am still not able to use LoRA in A1111.
Code to train LoRA:
Code to convert to A1111 format
System info
Beta Was this translation helpful? Give feedback.
All reactions